Chapter 5 Compositional analysis

load("data/data_podarcis_filfolensis.Rdata")
load("data/data_podarcis_gaigeae.Rdata")
load("data/data_podarcis_milensis.Rdata")
load("data/data_podarcis_pityusensis.Rdata")
load("data/data_podarcis_all.Rdata")

5.1 Taxonomy barplots

5.1.1 Podarcis filfolensis

genome_counts_filt_pf %>%
  mutate_at(vars(-genome),~./sum(.)) %>% #apply TSS nornalisation
  pivot_longer(-genome, names_to = "sample", values_to = "count") %>% #reduce to minimum number of columns
  left_join(., genome_metadata_pf, by = join_by(genome == genome)) %>% #append genome metadata
  left_join(., sample_metadata_pf, by = join_by(sample == sample)) %>% #append sample metadata
  filter(!is.na(count)) %>%
  ggplot(aes(y=count,x=sample, fill=phylum, group=phylum)) + #grouping enables keeping the same sorting of taxonomic units
    geom_bar(stat="identity", colour="white", linewidth=0.1) + #plot stacked bars with white borders
    scale_fill_manual(values=phylum_colors_pf) +
    labs(x = "Relative abundance", y ="Samples") +
    facet_nested(. ~ population,  scales="free", space="free") + #facet per day and treatment
    scale_y_continuous(expand = c(0.001, 0.001)) +
    theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1),
          axis.title.x = element_blank(),
          panel.background = element_blank(),
          panel.border = element_blank(),
          panel.grid.major = element_blank(),
          panel.grid.minor = element_blank(),
          axis.line = element_line(linewidth = 0.5, linetype = "solid", colour = "black"),
          legend.position = "none",
          strip.background.x=element_rect(color = NA, fill= "#f4f4f4"))

genome_counts_filt_pg %>%
  mutate_at(vars(-genome),~./sum(.)) %>% #apply TSS nornalisation
  pivot_longer(-genome, names_to = "sample", values_to = "count") %>% #reduce to minimum number of columns
  left_join(., genome_metadata_pg, by = join_by(genome == genome)) %>% #append genome metadata
  left_join(., sample_metadata_pg, by = join_by(sample == sample)) %>% #append sample metadata
  filter(!is.na(count)) %>%
  ggplot(aes(y=count,x=sample, fill=phylum, group=phylum)) + #grouping enables keeping the same sorting of taxonomic units
    geom_bar(stat="identity", colour="white", linewidth=0.1) + #plot stacked bars with white borders
    scale_fill_manual(values=phylum_colors_pg) +
    labs(x = "Relative abundance", y ="Samples") +
    facet_nested(. ~ population,  scales="free", space="free") + #facet per day and treatment
    scale_y_continuous(expand = c(0.001, 0.001)) +
    theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1),
          axis.title.x = element_blank(),
          panel.background = element_blank(),
          panel.border = element_blank(),
          panel.grid.major = element_blank(),
          panel.grid.minor = element_blank(),
          axis.line = element_line(linewidth = 0.5, linetype = "solid", colour = "black"),
          legend.position = "none",
          strip.background.x=element_rect(color = NA, fill= "#f4f4f4"))

genome_counts_filt_pm %>%
  mutate_at(vars(-genome),~./sum(.)) %>% #apply TSS nornalisation
  pivot_longer(-genome, names_to = "sample", values_to = "count") %>% #reduce to minimum number of columns
  left_join(., genome_metadata_pm, by = join_by(genome == genome)) %>% #append genome metadata
  left_join(., sample_metadata_pm, by = join_by(sample == sample)) %>% #append sample metadata
  filter(!is.na(count)) %>%
  ggplot(aes(y=count,x=sample, fill=phylum, group=phylum)) + #grouping enables keeping the same sorting of taxonomic units
    geom_bar(stat="identity", colour="white", linewidth=0.1) + #plot stacked bars with white borders
    scale_fill_manual(values=phylum_colors_pm) +
    labs(x = "Relative abundance", y ="Samples") +
    facet_nested(. ~ population,  scales="free", space="free") + #facet per day and treatment
    scale_y_continuous(expand = c(0.001, 0.001)) +
    theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1),
          axis.title.x = element_blank(),
          panel.background = element_blank(),
          panel.border = element_blank(),
          panel.grid.major = element_blank(),
          panel.grid.minor = element_blank(),
          axis.line = element_line(linewidth = 0.5, linetype = "solid", colour = "black"),
          legend.position = "none",
          strip.background.x=element_rect(color = NA, fill= "#f4f4f4"))

genome_counts_filt_pp %>%
  mutate_at(vars(-genome),~./sum(.)) %>% #apply TSS nornalisation
  pivot_longer(-genome, names_to = "sample", values_to = "count") %>% #reduce to minimum number of columns
  left_join(., genome_metadata_pp, by = join_by(genome == genome)) %>% #append genome metadata
  left_join(., sample_metadata_pp, by = join_by(sample == sample)) %>% #append sample metadata
  filter(!is.na(count)) %>%
  ggplot(aes(y=count,x=sample, fill=phylum, group=phylum)) + #grouping enables keeping the same sorting of taxonomic units
    geom_bar(stat="identity", colour="white", linewidth=0.1) + #plot stacked bars with white borders
    scale_fill_manual(values=phylum_colors_pp) +
    labs(x = "Relative abundance", y ="Samples") +
    facet_nested(. ~ population,  scales="free", space="free") + #facet per day and treatment
    scale_y_continuous(expand = c(0.001, 0.001)) +
    theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1),
          axis.title.x = element_blank(),
          panel.background = element_blank(),
          panel.border = element_blank(),
          panel.grid.major = element_blank(),
          panel.grid.minor = element_blank(),
          axis.line = element_line(linewidth = 0.5, linetype = "solid", colour = "black"),
          legend.position = "none",
          strip.background.x=element_rect(color = NA, fill= "#f4f4f4"))

5.2 Taxonomic representation

5.2.1 Phylum

phylum_summary <- genome_counts_filt_all %>%
  mutate_at(vars(-genome),~./sum(.)) %>% #apply TSS nornalisation
  pivot_longer(-genome, names_to = "sample", values_to = "count") %>% #reduce to minimum number of columns
  left_join(sample_metadata_all, by = join_by(sample == sample)) %>% #append sample metadata
  left_join(genome_metadata_all, by = join_by(genome == genome)) %>% #append genome metadata
  group_by(sample,phylum) %>%
  summarise(relabun=sum(count))

phylum_summary %>%
    filter(!is.na(relabun)) %>%
    group_by(phylum) %>%
    summarise(mean=mean(relabun),sd=sd(relabun)) %>%
    mutate(phylum= sub("^p__", "", phylum)) %>%
    arrange(-mean) %>%
    tt()

phylum	mean	sd
Bacillota_A	4.355073e-01	0.1637303694
Bacteroidota	3.795311e-01	0.1493442024
Bacillota	6.693929e-02	0.0613238855
Pseudomonadota	4.237993e-02	0.0659965403
Desulfobacterota	1.762937e-02	0.0168493333
Campylobacterota	1.394838e-02	0.0229133933
Cyanobacteriota	8.474584e-03	0.0120549930
Verrucomicrobiota	8.226209e-03	0.0140684507
Bacillota_C	6.505350e-03	0.0077147585
Spirochaetota	5.445050e-03	0.0249843346
Bacillota_B	4.111308e-03	0.0057340543
Fusobacteriota	3.024136e-03	0.0134489815
Halobacteriota	2.947999e-03	0.0105666272
Actinomycetota	2.221294e-03	0.0190806008
Chlamydiota	1.109162e-03	0.0112564276
Elusimicrobiota	1.104802e-03	0.0036746035
Synergistota	3.666072e-04	0.0024311729
Planctomycetota	1.908305e-04	0.0017144286
	1.473864e-04	0.0009299590
Deferribacterota	1.413909e-04	0.0006340007
Thermoplasmatota	4.851518e-05	0.0006362706

phylum_arrange <- phylum_summary %>%
    filter(!is.na(relabun)) %>%
    group_by(phylum) %>%
    summarise(mean=sum(relabun)) %>%
    arrange(-mean) %>%
    select(phylum) %>%
    #mutate(phylum= sub("^p__", "", phylum)) %>%
    pull()

phylum_summary %>%
    left_join(genome_metadata_all %>% select(phylum) %>% unique(),by="phylum") %>%
    left_join(sample_metadata_all,by=join_by(sample==sample)) %>%
    filter(phylum != "p__") %>% 
    #mutate(phylum= sub("^p__", "", phylum)) %>%
    filter(phylum %in% phylum_arrange[1:20]) %>%
    mutate(phylum=factor(phylum,levels=rev(phylum_arrange[1:20]))) %>%
    filter(relabun > 0) %>%
    ggplot(aes(x=relabun, y=phylum, group=phylum, color=phylum, fill=phylum)) +
        scale_color_manual(values=phylum_colors_all) +
        scale_fill_manual(values=phylum_colors_all) +
        geom_jitter(alpha=0.5) + 
        facet_nested(. ~ species)+
        theme_minimal() +
        theme(legend.position = "none")

5.2.2 Order

order_summary <- genome_counts_filt_all %>%
  mutate_at(vars(-genome),~./sum(.)) %>% #apply TSS nornalisation
  pivot_longer(-genome, names_to = "sample", values_to = "count") %>% #reduce to minimum number of columns
  left_join(sample_metadata_all %>% rename(host_order=order), by = join_by(sample == sample)) %>% #append sample metadata
  left_join(genome_metadata_all, by = join_by(genome == genome)) %>% #append genome metadata
  group_by(sample,order) %>%
  summarise(relabun=sum(count))

order_summary %>%
    filter(!is.na(relabun)) %>%
    group_by(order) %>%
    summarise(mean=mean(relabun),sd=sd(relabun)) %>%
    mutate(famorderily= sub("^o__", "", order)) %>%
    arrange(-mean) %>%
    tt()

order	mean	sd	famorderily
o__Bacteroidales	3.795311e-01	0.1493442024	Bacteroidales
o__Lachnospirales	2.817732e-01	0.1573578010	Lachnospirales
o__Oscillospirales	7.730821e-02	0.0482442135	Oscillospirales
o__Christensenellales	6.152228e-02	0.0521531204	Christensenellales
o__Erysipelotrichales	3.205759e-02	0.0472082321	Erysipelotrichales
o__Desulfovibrionales	1.762937e-02	0.0168493333	Desulfovibrionales
o__Enterobacterales	1.596443e-02	0.0397310018	Enterobacterales
o__Campylobacterales	1.394838e-02	0.0229133933	Campylobacterales
o__Mycoplasmatales	9.674457e-03	0.0201025198	Mycoplasmatales
o__Acholeplasmatales	9.244018e-03	0.0156078657	Acholeplasmatales
o__Gastranaerophilales	8.474584e-03	0.0120549930	Gastranaerophilales
o__RF32	7.907507e-03	0.0109564629	RF32
o__RF39	7.616380e-03	0.0129867266	RF39
o__Verrucomicrobiales	7.557137e-03	0.0136890242	Verrucomicrobiales
o__Enterobacterales_A	6.146616e-03	0.0225932402	Enterobacterales_A
o__RFN20	5.491908e-03	0.0134551586	RFN20
o__TANB77	5.387227e-03	0.0091071005	TANB77
o__Peptostreptococcales	4.806343e-03	0.0075471530	Peptostreptococcales
o__UBA3830	4.368400e-03	0.0098939122	UBA3830
o__Clostridiales	4.071744e-03	0.0181994301	Clostridiales
o__Selenomonadales	3.953551e-03	0.0066974902	Selenomonadales
o__Peptococcales	3.689298e-03	0.0055754286	Peptococcales
o__Sphaerochaetales	3.529054e-03	0.0216011752	Sphaerochaetales
o__Diplorickettsiales	3.505108e-03	0.0459055178	Diplorickettsiales
o__Fusobacteriales	3.024136e-03	0.0134489815	Fusobacteriales
o__Acidaminococcales	2.551799e-03	0.0049055131	Acidaminococcales
o__Methanosarcinales	2.372541e-03	0.0097274543	Methanosarcinales
o__RUG11792	2.184233e-03	0.0053494956	RUG11792
o__Actinomycetales	1.561179e-03	0.0190765399	Actinomycetales
o__Lactobacillales	1.265853e-03	0.0051617233	Lactobacillales
o__Chlamydiales	1.109162e-03	0.0112564276	Chlamydiales
o__Elusimicrobiales	1.104802e-03	0.0036746035	Elusimicrobiales
o__ML615J-28	9.826848e-04	0.0037803511	ML615J-28
o__Brevinematales	8.957611e-04	0.0046437768	Brevinematales
o__GWE2-31-10	8.620607e-04	0.0040717621	GWE2-31-10
o__Coriobacteriales	6.601149e-04	0.0013420095	Coriobacteriales
o__CAJFEE01	6.063947e-04	0.0028904690	CAJFEE01
o__Methanomicrobiales	5.754579e-04	0.0026410958	Methanomicrobiales
o__	5.717583e-04	0.0021241114
o__Rs-D84	5.603757e-04	0.0031715201	Rs-D84
o__Rickettsiales	5.287290e-04	0.0027549629	Rickettsiales
o__UBA1381	5.035832e-04	0.0015475012	UBA1381
o__Opitutales	4.901270e-04	0.0018532230	Opitutales
o__Synergistales	3.666072e-04	0.0024311729	Synergistales
o__Pseudomonadales	3.626249e-04	0.0029135461	Pseudomonadales
o__UBA7702	2.450743e-04	0.0015747068	UBA7702
o__Cardiobacteriales	2.276453e-04	0.0029855408	Cardiobacteriales
o__Pirellulales	1.908305e-04	0.0017144286	Pirellulales
o__Victivallales	1.789455e-04	0.0015054509	Victivallales
o__UBA4068	1.769355e-04	0.0005665926	UBA4068
o__Burkholderiales	1.721286e-04	0.0007779434	Burkholderiales
o__Treponematales	1.581747e-04	0.0008279556	Treponematales
o__Deferribacterales	1.413909e-04	0.0006340007	Deferribacterales
o__UMGS1883	7.335614e-05	0.0004670412	UMGS1883
o__Methanomassiliicoccales	4.851518e-05	0.0006362706	Methanomassiliicoccales
o__Eubacteriales	3.408400e-05	0.0001552477	Eubacteriales
o__Rhodobacterales	2.776073e-05	0.0003101775	Rhodobacterales
o__Tissierellales	2.729052e-05	0.0003579118	Tissierellales

order_arrange <- order_summary %>%
    filter(!is.na(relabun)) %>%
    group_by(order) %>%
    summarise(mean=sum(relabun)) %>%
    arrange(-mean) %>%
    select(order) %>%
    mutate(order= sub("^o__", "", order)) %>%
    pull()

order_summary %>%
    left_join(genome_metadata_all %>% select(order,phylum) %>% unique(),by="order") %>%
    left_join(sample_metadata_all %>% rename(host_order=order),by="sample") %>%
    filter(order != "o__") %>% 
    mutate(order= sub("^o__", "", order)) %>%
    filter(order %in% order_arrange[1:20]) %>%
    mutate(order=factor(order,levels=rev(order_arrange[1:20]))) %>%
    filter(relabun > 0) %>%
    ggplot(aes(x=relabun, y=order, group=order, color=phylum, fill=phylum)) +
        scale_color_manual(values=phylum_colors_all) +
        scale_fill_manual(values=phylum_colors_all) +
        #geom_boxplot(alpha=0.2) +
        geom_jitter(alpha=0.5) + 
        facet_nested(. ~ species)+
        theme_minimal() +
        theme(legend.position = "none")

5.2.3 Family

family_summary <- genome_counts_filt_all %>%
  mutate_at(vars(-genome),~./sum(.)) %>% #apply TSS nornalisation
  pivot_longer(-genome, names_to = "sample", values_to = "count") %>% #reduce to minimum number of columns
  left_join(sample_metadata_all, by = join_by(sample == sample)) %>% #append sample metadata
  left_join(genome_metadata_all, by = join_by(genome == genome)) %>% #append genome metadata
  group_by(sample,family) %>%
  summarise(relabun=sum(count))

family_summary %>%
    filter(!is.na(relabun)) %>%
    group_by(family) %>%
    summarise(mean=mean(relabun),sd=sd(relabun)) %>%
    mutate(family= sub("^f__", "", family)) %>%
    arrange(-mean) %>%
    tt()

family	mean	sd
Lachnospiraceae	2.679049e-01	1.479098e-01
Bacteroidaceae	2.128971e-01	1.133002e-01
Tannerellaceae	7.843675e-02	4.086968e-02
Rikenellaceae	4.521289e-02	3.594946e-02
Marinifilaceae	3.815762e-02	3.130093e-02
Ruminococcaceae	3.516717e-02	2.681469e-02
UBA3700	3.100225e-02	3.669198e-02
Oscillospiraceae	2.542478e-02	2.063380e-02
Erysipelotrichaceae	2.220306e-02	3.495105e-02
	1.854607e-02	2.537000e-02
Desulfovibrionaceae	1.762937e-02	1.684933e-02
Enterobacteriaceae	1.596443e-02	3.973100e-02
Helicobacteraceae	1.394838e-02	2.291339e-02
Acutalibacteraceae	1.129138e-02	2.182770e-02
Coprobacillaceae	9.854533e-03	1.610175e-02
Mycoplasmoidaceae	9.198005e-03	1.988191e-02
Pumilibacteraceae	8.303712e-03	2.717791e-02
UBA660	7.616380e-03	1.298673e-02
Akkermansiaceae	7.557137e-03	1.368902e-02
CAG-239	7.371042e-03	9.989587e-03
Gastranaerophilaceae	7.216239e-03	1.061888e-02
Anaerotignaceae	6.013824e-03	8.783101e-03
Anaeroplasmataceae	5.687338e-03	1.422618e-02
Butyricicoccaceae	5.289808e-03	6.576968e-03
CAG-74	4.607693e-03	1.032186e-02
CAG-508	4.495099e-03	8.141235e-03
Anaerovoracaceae	4.441054e-03	7.271621e-03
Vibrionaceae	4.421724e-03	1.848524e-02
Clostridiaceae	4.071744e-03	1.819943e-02
DTU072	3.904841e-03	7.233438e-03
Peptococcaceae	3.689298e-03	5.575429e-03
CAG-449	3.598003e-03	1.246597e-02
Sphaerochaetaceae	3.529054e-03	2.160118e-02
WRBM01	3.523614e-03	6.291393e-03
Diplorickettsiaceae	3.505108e-03	4.590552e-02
UBA932	3.368690e-03	8.602302e-03
Fusobacteriaceae	3.024136e-03	1.344898e-02
CAG-917	2.786813e-03	1.051273e-02
Acidaminococcaceae	2.551799e-03	4.905513e-03
Methanosarcinaceae	2.372541e-03	9.727454e-03
Borkfalkiaceae	2.215945e-03	9.726245e-03
UBA1242	1.975129e-03	4.034220e-03
CAG-274	1.901813e-03	4.757881e-03
Aeromonadaceae	1.724892e-03	1.089339e-02
CAG-288	1.623242e-03	5.036122e-03
Micrococcaceae	1.546507e-03	1.907650e-02
MGBC116941	1.403668e-03	4.908522e-03
CALTSX01	1.109162e-03	1.125643e-02
Elusimicrobiaceae	1.104802e-03	3.674604e-03
CAG-314	1.067128e-03	3.487523e-03
CAG-138	1.028579e-03	6.324693e-03
CALVMC01	9.864994e-04	3.349719e-03
RUG14156	9.300233e-04	2.736356e-03
UBA3830	9.142222e-04	2.758943e-03
Brevinemataceae	8.957611e-04	4.643777e-03
GWE2-31-10	8.620607e-04	4.071762e-03
Eggerthellaceae	6.601149e-04	1.342009e-03
CAJFEE01	6.063947e-04	2.890469e-03
Methanocorpusculaceae	5.754579e-04	2.641096e-03
Rs-D84	5.603757e-04	3.171520e-03
Muribaculaceae	5.226674e-04	3.051788e-03
CAG-313	5.117558e-04	2.193878e-03
UBA1381	5.035832e-04	1.547501e-03
LL51	4.763559e-04	1.852608e-03
CAG-698	4.709290e-04	2.164469e-03
UBA1997	4.208195e-04	2.382923e-03
Streptococcaceae	4.160441e-04	2.630200e-03
Enterococcaceae	4.090411e-04	1.517990e-03
CAG-465	3.788372e-04	1.164817e-03
Coprobacteraceae	3.767262e-04	1.347094e-03
Synergistaceae	3.666072e-04	2.431173e-03
Peptostreptococcaceae	3.652882e-04	1.348669e-03
Pseudomonadaceae	3.626249e-04	2.913546e-03
Massilibacillaceae	3.253008e-04	1.474960e-03
UBA3637	3.139388e-04	1.531614e-03
Metamycoplasmataceae	3.110466e-04	3.810180e-03
CHK158-818	3.095362e-04	9.740463e-04
CAG-631	2.706635e-04	1.015132e-03
Lactobacillaceae	2.576707e-04	2.262342e-03
UBA7702	2.450743e-04	1.574707e-03
Wohlfahrtiimonadaceae	2.276453e-04	2.985541e-03
CAG-977	2.225261e-04	1.355731e-03
SIG350	2.069507e-04	2.714132e-03
Thermoguttaceae	1.908305e-04	1.714429e-03
CAJFVJ01	1.892159e-04	1.389700e-03
Burkholderiaceae	1.721286e-04	7.779434e-04
Hepatoplasmataceae	1.654048e-04	1.179092e-03
Treponemataceae	1.581747e-04	8.279556e-04
UBA5755	1.525827e-04	5.351000e-04
Mucispirillaceae	1.413909e-04	6.340007e-04
UBA1234	1.381659e-04	5.154643e-04
Catellicoccaceae	9.608682e-05	8.591908e-04
CAG-272	9.588815e-05	7.206419e-04
Vagococcaceae	8.701072e-05	1.141135e-03
Victivallaceae	7.718385e-05	4.488404e-04
Azobacteroidaceae	7.440778e-05	9.758489e-04
UMGS1883	7.335614e-05	4.670412e-04
Cellulosilyticaceae	5.332328e-05	3.808652e-04
Methanomethylophilaceae	4.851518e-05	6.362706e-04
DUVY01	4.637858e-05	5.673763e-04
Paludibacteraceae	4.504653e-05	2.212459e-04
CAG-382	3.918633e-05	1.936551e-04
Eubacteriaceae	3.408400e-05	1.552477e-04
JAEDCM01	3.306564e-05	4.336518e-04
Rhodobacteraceae	2.776073e-05	3.101775e-04
Peptoniphilaceae	2.729052e-05	3.579118e-04
HGM11417	2.626128e-05	1.876693e-04
UBA4068	2.435275e-05	9.859687e-05
Microbacteriaceae	1.467237e-05	1.924263e-04
UBA9783	1.377110e-05	1.243972e-04
WCHB1-69	5.663380e-06	7.427454e-05

family_arrange <- family_summary %>%
    filter(!is.na(relabun)) %>%
    group_by(family) %>%
    summarise(mean=sum(relabun)) %>%
    arrange(-mean) %>%
    select(family) %>%
    mutate(family= sub("^f__", "", family)) %>%
    pull()

family_summary %>%
    left_join(genome_metadata_all %>% select(family,phylum) %>% unique(),by=join_by(family==family)) %>%
    left_join(sample_metadata_all,by=join_by(sample==sample)) %>%
    filter(family != "f__") %>% 
    mutate(family= sub("^f__", "", family)) %>%
    filter(family %in% family_arrange[1:20]) %>%
    mutate(family=factor(family,levels=rev(family_arrange[1:20]))) %>%
    filter(relabun > 0) %>%
    ggplot(aes(x=relabun, y=family, group=family, color=phylum, fill=phylum)) +
        scale_color_manual(values=phylum_colors_all) +
        scale_fill_manual(values=phylum_colors_all) +
        #geom_boxplot(alpha=0.2) +
        geom_jitter(alpha=0.5) + 
        facet_nested(. ~ species)+
        theme_minimal() +
        theme(legend.position = "none")

5.2.4 Genus

genus_summary <- genome_counts_filt_all %>%
  mutate_at(vars(-genome),~./sum(.)) %>% #apply TSS nornalisation
  pivot_longer(-genome, names_to = "sample", values_to = "count") %>% #reduce to minimum number of columns
  left_join(sample_metadata_all, by = join_by(sample == sample)) %>% #append sample metadata
  left_join(genome_metadata_all, by = join_by(genome == genome)) %>% #append genome metadata
  group_by(sample,genus) %>%
  summarise(relabun=sum(count)) %>%
  filter(genus != "g__")

genus_summary %>%
    filter(!is.na(relabun)) %>%
    group_by(genus) %>%
    summarise(mean=mean(relabun),sd=sd(relabun)) %>%
    arrange(-mean) %>%
    tt()

genus	mean	sd
g__Bacteroides	1.492633e-01	9.145770e-02
g__Parabacteroides	6.838309e-02	3.825177e-02
g__Phocaeicola	5.590755e-02	4.767695e-02
g__Odoribacter	3.698228e-02	3.157692e-02
g__Alistipes	3.688633e-02	3.262665e-02
g__Kineothrix	3.485495e-02	7.746321e-02
g__JAAYNV01	3.180220e-02	5.544362e-02
g__Roseburia	2.034157e-02	6.055895e-02
g__Acetatifactor	1.353817e-02	2.662322e-02
g__Ventrimonas	1.119879e-02	1.784188e-02
g__CAG-95	1.116264e-02	2.245897e-02
g__Helicobacter_J	1.041623e-02	1.995870e-02
g__Parabacteroides_B	9.901565e-03	1.173939e-02
g__Breznakia	9.810792e-03	2.108634e-02
g__Mycoplasmoides	9.198005e-03	1.988191e-02
g__Akkermansia	7.557137e-03	1.368902e-02
g__Velocimicrobium	7.454088e-03	1.907730e-02
g__RGIG4733	7.157888e-03	2.514900e-02
g__Hungatella_A	6.350838e-03	9.898917e-03
g__UBA866	5.974162e-03	1.279000e-02
g__Desulfovibrio	5.709603e-03	9.315901e-03
g__Anaerotruncus	5.630278e-03	7.811119e-03
g__Thomasclavelia	5.493662e-03	1.248939e-02
g__Intestinimonas	5.301231e-03	6.478704e-03
g__Bilophila	5.134848e-03	6.647822e-03
g__Ruthenibacterium	4.907256e-03	9.923689e-03
g__Enterocloster	4.615640e-03	6.281140e-03
g__JALFVM01	4.503361e-03	1.060918e-02
g__Vibrio	4.421724e-03	1.848524e-02
g__Hespellia	4.402515e-03	1.129796e-02
g__Fimenecus	4.242280e-03	1.435771e-02
g__14-2	3.563480e-03	1.647062e-02
g__Clostridium_Q	3.535110e-03	4.975653e-03
g__NHYM01	3.532146e-03	9.913909e-03
g__Spiro-02	3.529054e-03	2.160118e-02
g__Aquirickettsiella	3.505108e-03	4.590552e-02
g__Copromonas	3.447747e-03	4.581581e-03
g__Lawsonibacter	3.443311e-03	5.211912e-03
g__Egerieousia	3.368690e-03	8.602302e-03
g__Protoclostridium	3.296536e-03	2.553531e-02
g__Enterobacter	3.191565e-03	1.402631e-02
g__Lacrimispora	3.189242e-03	7.287909e-03
g__Oscillibacter	3.157271e-03	4.419607e-03
g__CHH4-2	3.075367e-03	5.253794e-03
g__Escherichia	3.000053e-03	1.115703e-02
g__Limiplasma	2.969019e-03	7.133192e-03
g__Rikenella	2.939128e-03	6.055218e-03
g__Sarcina	2.877939e-03	1.630802e-02
g__CAZU01	2.870401e-03	4.887287e-03
g__Fusobacterium_A	2.859566e-03	1.339771e-02
g__Dielma	2.815223e-03	6.874781e-03
g__OM05-12	2.791990e-03	5.749748e-03
g__Phascolarctobacterium	2.551799e-03	4.905513e-03
g__Fimivivens	2.467945e-03	3.688432e-03
g__MGBC136627	2.446550e-03	6.005822e-03
g__MGBC143606	2.440758e-03	7.414283e-03
g__Methanimicrococcus	2.372541e-03	9.727454e-03
g__Intestinibacillus	2.365302e-03	5.280365e-03
g__Hungatella	2.292660e-03	4.692286e-03
g__Mailhella	2.254541e-03	3.960166e-03
g__Pseudoflavonifractor	2.140159e-03	5.519017e-03
g__Gemmiger	2.112060e-03	6.521526e-03
g__MGBC140009	2.031711e-03	5.716638e-03
g__Lachnotalea	2.012696e-03	5.442239e-03
g__Pelethenecus	2.008513e-03	8.013717e-03
g__WRDF01	1.983926e-03	3.923816e-03
g__MGBC131033	1.973766e-03	3.165900e-03
g__Dysosmobacter	1.947698e-03	2.768625e-03
g__Negativibacillus	1.942876e-03	4.332910e-03
g__Coprobacillus	1.934097e-03	3.859945e-03
g__Angelakisella	1.884111e-03	3.631754e-03
g__RGIG6463	1.836103e-03	3.631321e-03
g__MGBC165282	1.805128e-03	4.854526e-03
g__Buttiauxella	1.783363e-03	6.842193e-03
g__JAAYQI01	1.771220e-03	3.100609e-03
g__Limenecus	1.757957e-03	3.763048e-03
g__Aeromonas	1.724892e-03	1.089339e-02
g__Agathobaculum	1.691308e-03	3.310944e-03
g__Citrobacter	1.678009e-03	7.050371e-03
g__Coproplasma	1.676723e-03	9.512497e-03
g__SZUA-378	1.657792e-03	1.399271e-02
g__Bacteroides_E	1.646079e-03	2.158813e-02
g__Eisenbergiella	1.567253e-03	3.864070e-03
g__Acaricomes	1.546507e-03	1.907650e-02
g__SIG332	1.531952e-03	9.459875e-03
g__CAG-269	1.410352e-03	3.725174e-03
g__SIG299	1.380919e-03	7.119758e-03
g__NSJ-61	1.352789e-03	4.082352e-03
g__RGIG3002	1.316711e-03	4.431909e-03
g__Marseille-P3106	1.288557e-03	2.227308e-03
g__WRHT01	1.286176e-03	3.892975e-03
g__Kosakonia	1.279803e-03	1.185315e-02
g__Emergencia	1.251317e-03	4.473343e-03
g__UMGS1251	1.238852e-03	3.182570e-03
g__Tidjanibacter	1.233090e-03	3.465801e-03
g__C-19	1.222456e-03	4.824577e-03
g__Clostridium	1.193805e-03	7.940942e-03
g__Butyricimonas	1.175332e-03	2.982029e-03
g__MGBC116941	1.143994e-03	4.759873e-03
g__Anaerotignum	1.131763e-03	1.921774e-03
g__Evtepia	1.125245e-03	2.346285e-03
g__Scatousia	1.113860e-03	3.186063e-03
g__Scandinavium	1.110443e-03	1.289658e-02
g__CALTSX01	1.109162e-03	1.125643e-02
g__Anaeroplasma	1.099325e-03	4.010838e-03
g__UBA2658	1.093757e-03	2.645590e-03
g__Blautia_A	1.062518e-03	2.897013e-03
g__Proteus	1.058683e-03	1.335374e-02
g__Ruminococcus_E	1.029855e-03	6.336954e-03
g__JAHHSE01	1.016881e-03	2.081230e-03
g__Anaerostipes	9.993568e-04	6.214220e-03
g__CAJLXD01	9.907104e-04	2.932215e-03
g__Phocaeicola_A	9.892770e-04	4.013536e-03
g__Fournierella	9.581274e-04	2.619171e-03
g__CAG-345	9.417628e-04	4.156477e-03
g__Brevinema	8.957611e-04	4.643777e-03
g__Harryflintia	8.884142e-04	2.505438e-03
g__C-53	8.874160e-04	4.469056e-03
g__Acutalibacter	8.861698e-04	1.776887e-03
g__Aminipila	8.810006e-04	2.463410e-03
g__Spyradomonas	8.525628e-04	4.191135e-03
g__Ventrenecus	8.497155e-04	2.794178e-03
g__CAG-273	8.444700e-04	4.049118e-03
g__Caccovivens	8.366088e-04	2.621483e-03
g__VSOB01	8.152912e-04	3.184675e-03
g__CAG-1782	7.959184e-04	3.106148e-03
g__RGIG1896	7.925359e-04	1.323233e-03
g__Ruminiclostridium_E	7.797273e-04	3.917287e-03
g__CAG-582	7.735000e-04	4.481513e-03
g__Blautia	7.711825e-04	1.670642e-03
g__Klebsiella	7.596956e-04	3.591632e-03
g__Bariatricus	7.585807e-04	1.661520e-03
g__Extibacter	7.391720e-04	1.570615e-03
g__Stoquefichus	7.391191e-04	3.131298e-03
g__CALURL01	7.372695e-04	2.459028e-03
g__JAAWBF01	7.270628e-04	2.291304e-03
g__UBA1436	7.244074e-04	2.911088e-03
g__UBA5578	6.989678e-04	4.423923e-03
g__IOR16	6.837972e-04	1.623524e-03
g__CAG-288	6.814792e-04	2.646198e-03
g__Clostridium_AI	6.796597e-04	7.646021e-03
g__MGBC133411	6.731026e-04	1.995666e-03
g__CALUVN01	6.547298e-04	1.647970e-03
g__Scatenecus	6.527575e-04	2.463681e-03
g__UBA7185	6.237137e-04	2.850324e-03
g__Faecousia	6.199737e-04	2.757282e-03
g__Muricomes	6.193494e-04	2.526333e-03
g__Scatacola_A	6.113889e-04	2.209083e-03
g__Faecalibacillus	6.073162e-04	3.608509e-03
g__Harrysmithimonas	6.063947e-04	2.890469e-03
g__CAJTFG01	5.848933e-04	3.604164e-03
g__Bacilliculturomica	5.704876e-04	1.402287e-03
g__Faecisoma	5.592534e-04	2.521527e-03
g__Methanocorpusculum	5.525498e-04	2.600043e-03
g__Anaerocaecibacter	5.522731e-04	2.721369e-03
g__CAKQDS01	5.418129e-04	2.199150e-03
g__Salmonella	5.276877e-04	4.414352e-03
g__RGIG8482	5.219404e-04	1.949521e-03
g__Galloscillospira_A	5.158552e-04	9.715988e-04
g__Fimivicinus	5.153979e-04	2.165963e-03
g__Fimimorpha	4.980684e-04	2.338325e-03
g__JAGAJR01	4.971561e-04	3.285758e-03
g__Caccenecus	4.949970e-04	1.527726e-03
g__UBA1794	4.933027e-04	1.707288e-03
g__UBA1417	4.791205e-04	1.029684e-03
g__UBA940	4.740035e-04	1.712347e-03
g__CAJFPI01	4.629136e-04	1.001336e-03
g__Lactonifactor	4.603409e-04	1.417494e-03
g__Clostridium_AQ	4.466972e-04	1.736532e-03
g__Onthovicinus	4.445381e-04	2.331257e-03
g__Buchnera	4.433102e-04	5.813959e-03
g__Clostridium_N	4.402910e-04	2.950622e-03
g__CAKRHR01	4.367869e-04	2.278772e-03
g__DXYV01	4.360731e-04	1.398616e-03
g__RGIG1902	4.283551e-04	7.371513e-04
g__SIG32	4.227733e-04	1.529877e-03
g__HGM11386	4.218531e-04	1.727808e-03
g__Butyrivibrio_A	4.136198e-04	3.448206e-03
g__FLUQ01	4.120756e-04	9.918380e-04
g__CAG-590	4.073011e-04	1.856155e-03
g__Faecimonas	4.024457e-04	1.952064e-03
g__MGBC107952	4.009827e-04	1.132923e-03
g__Ventrisoma	3.996970e-04	1.047519e-03
g__Beduini	3.891743e-04	1.496954e-03
g__RUG14156	3.667219e-04	1.782969e-03
g__Cloacibacillus	3.666072e-04	2.431173e-03
g__Pseudomonas	3.626249e-04	2.913546e-03
g__Lawsonia	3.609631e-04	2.976114e-03
g__Marvinbryantia	3.602193e-04	1.589621e-03
g__CAG-465	3.584980e-04	1.153031e-03
g__Coprobacter	3.568144e-04	1.332767e-03
g__HGM12998	3.510965e-04	1.268564e-03
g__Faecenecus	3.477335e-04	1.547966e-03
g__RACS-047	3.410345e-04	1.305915e-03
g__RGIG4097	3.394551e-04	2.512766e-03
g__CAG-303	3.354250e-04	2.253817e-03
g__Paraeggerthella	3.306477e-04	7.881768e-04
g__Scatavimonas	3.292069e-04	2.998578e-03
g__Scatocola	3.170079e-04	2.010498e-03
g__CAKTEE01	3.148626e-04	1.817047e-03
g__UBA7488	3.139388e-04	1.531614e-03
g__Caccomorpha	3.135442e-04	8.132352e-04
g__UBA710	3.110466e-04	3.810180e-03
g__Gallibacteroides	3.095362e-04	9.740463e-04
g__Lachnospira	3.070567e-04	1.867816e-03
g__CALXUC01	3.067121e-04	1.882934e-03
g__JAIHAL01	2.938058e-04	1.765062e-03
g__Zag111	2.895640e-04	1.695054e-03
g__Ventricola	2.878743e-04	1.507071e-03
g__Scatomorpha	2.765635e-04	7.278705e-04
g__Lachnoclostridium_B	2.763740e-04	8.906298e-04
g__UBA5026	2.752265e-04	1.128502e-03
g__Caccosoma	2.706635e-04	1.015132e-03
g__Catenibacillus	2.681525e-04	7.308965e-04
g__JAGBWK01	2.667486e-04	2.985884e-03
g__RGIG4057	2.634560e-04	1.610134e-03
g__Oliverpabstia	2.606026e-04	2.224448e-03
g__UMGS1202	2.590747e-04	8.409060e-04
g__HGM05232	2.559188e-04	7.315989e-04
g__Merdicola	2.528427e-04	1.910082e-03
g__Cryptoclostridium	2.450743e-04	1.574707e-03
g__UMGS2016	2.439149e-04	1.057064e-03
g__CALXWF01	2.437349e-04	8.980698e-04
g__Onthocola_B	2.336122e-04	1.097069e-03
g__RUG14670	2.334104e-04	1.268072e-03
g__UMGS1663	2.320796e-04	1.174466e-03
g__Plesiomonas	2.292023e-04	2.122607e-03
g__SIG230	2.280915e-04	9.725989e-04
g__Butyricicoccus	2.280100e-04	1.179904e-03
g__Butyribacter	2.278963e-04	1.554091e-03
g__HGM13233	2.269566e-04	1.044833e-03
g__JAHHUA01	2.254978e-04	1.219591e-03
g__CALWZU01	2.244363e-04	7.795409e-04
g__CAG-977	2.225261e-04	1.355731e-03
g__Aphodocola	2.222897e-04	1.161474e-03
g__CALXRO01	2.218957e-04	1.970482e-03
g__Heteroruminococcus	2.202694e-04	9.244284e-04
g__JAJQAW01	2.169416e-04	7.681528e-04
g__Onthenecus	2.147993e-04	1.115093e-03
g__RGIG7389	2.135590e-04	6.700920e-04
g__Faecivivens	2.124632e-04	6.117535e-04
g__Onthousia	2.092884e-04	1.156334e-03
g__SIG350	2.069507e-04	2.714132e-03
g__Zhenpiania	2.019229e-04	4.491625e-04
g__WQYD01	2.010363e-04	7.107867e-04
g__Schmidhempelia	1.993159e-04	2.428842e-03
g__CAJKWP01	1.983903e-04	1.179880e-03
g__Enterococcus_B	1.954034e-04	9.681045e-04
g__JAILHT01	1.916321e-04	1.904125e-03
g__RGIG3701	1.908305e-04	1.714429e-03
g__Ignatzschineria	1.894434e-04	2.484527e-03
g__Avoscillospira_A	1.849958e-04	7.621367e-04
g__RUG12867	1.830035e-04	9.744369e-04
g__CAG-245	1.810191e-04	1.094579e-03
g__Anaerovorax	1.807911e-04	8.302159e-04
g__Raoultibacter	1.797664e-04	8.292516e-04
g__UMGS1585	1.752553e-04	7.702768e-04
g__Oxalobacter	1.721286e-04	7.779434e-04
g__Hafnia	1.709747e-04	1.378637e-03
g__CAG-510	1.665191e-04	8.640457e-04
g__Kluyvera	1.663693e-04	1.308586e-03
g__Hepatoplasma	1.654048e-04	1.179092e-03
g__UMGS75	1.626765e-04	1.435280e-03
g__JADFUS01	1.619273e-04	6.573895e-04
g__UBA7405	1.612771e-04	2.016590e-03
g__Streptococcus	1.564224e-04	2.051461e-03
g__CAG-56	1.525484e-04	6.872474e-04
g__CCUG-7971	1.523791e-04	6.252194e-04
g__Barb7	1.520997e-04	1.994769e-03
g__Gallispira	1.502610e-04	1.952849e-03
g__Lapidilactobacillus	1.409595e-04	1.848667e-03
g__Butyricicoccus_A	1.367025e-04	7.053366e-04
g__Limousia	1.360041e-04	6.955315e-04
g__Galligastranaerophilus	1.353461e-04	7.910321e-04
g__RGIG8607	1.330395e-04	8.153357e-04
g__Romboutsia_C	1.324145e-04	8.281891e-04
g__Enterococcus	1.324071e-04	8.356372e-04
g__Lactococcus_A	1.314638e-04	1.483600e-03
g__Leclercia	1.312203e-04	8.697175e-04
g__Pelethosoma	1.307797e-04	6.745119e-04
g__Lactococcus	1.281579e-04	7.899264e-04
g__MGBC124762	1.275812e-04	3.998533e-04
g__MGBC102946	1.258646e-04	5.024944e-04
g__CALXDZ01	1.242807e-04	4.083501e-04
g__Alectryocaccomicrobium	1.235486e-04	7.824254e-04
g__Avelusimicrobium	1.231087e-04	5.021372e-04
g__Murimonas	1.213808e-04	6.752085e-04
g__CALXIC01	1.201073e-04	4.762615e-04
g__Eubacterium_R	1.155168e-04	6.661566e-04
g__CAJMNU01	1.144585e-04	4.126897e-04
g__Metalachnospira	1.123175e-04	3.821465e-04
g__MGBC162267	1.119052e-04	5.900730e-04
g__JAEXFV01	1.108700e-04	5.225033e-04
g__UBA4636	1.101747e-04	5.696311e-04
g__Ruminococcus_G	1.085800e-04	5.727591e-04
g__JAHZFN01	1.041903e-04	4.947845e-04
g__Alistipes_A	1.023731e-04	3.424616e-04
g__Adamsella	1.005056e-04	8.259359e-04
g__JAAVYW01	9.886611e-05	3.596087e-04
g__UBA6345	9.776278e-05	5.890564e-04
g__UMGS1601	9.678895e-05	1.027188e-03
g__UMGS946	9.645721e-05	7.355573e-04
g__Catellicoccus	9.608682e-05	8.591908e-04
g__Novisyntrophococcus	9.472371e-05	6.442503e-04
g__CAG-41	9.123793e-05	6.894142e-04
g__CAG-307	9.056080e-05	6.397842e-04
g__CAKPCJ01	8.942488e-05	4.738890e-04
g__JAEWLZ01	8.871037e-05	1.125625e-03
g__Scybalousia	8.811278e-05	6.607347e-04
g__JAGZHZ01	8.729754e-05	5.699666e-04
g__Vagococcus	8.701072e-05	1.141135e-03
g__CAG-177	8.598892e-05	6.008884e-04
g__JALENY01	8.400275e-05	7.456506e-04
g__UBA1234	8.317669e-05	3.789843e-04
g__Eggerthella	8.252648e-05	3.589205e-04
g__Paraclostridium	8.049454e-05	6.908705e-04
g__UBA9414	7.948449e-05	4.143991e-04
g__Howiella	7.930957e-05	4.148145e-04
g__WRAV01	7.609451e-05	3.151892e-04
g__1XD8-76	7.561457e-05	5.115263e-04
g__Coprosoma	7.472227e-05	3.452372e-04
g__Symbiothrix	7.440778e-05	9.758489e-04
g__Eubacterium_F	7.419399e-05	4.473563e-04
g__CALVUN01	7.360091e-05	2.973254e-04
g__SIG471	7.262934e-05	2.760627e-04
g__PeH17	7.223390e-05	6.588230e-04
g__CALVXC01	7.196506e-05	6.695435e-04
g__RGIG4709	6.834702e-05	3.413827e-04
g__NSJ-51	6.807371e-05	2.871386e-04
g__Stercorousia	6.781125e-05	5.448313e-04
g__Gordonibacter	6.717435e-05	2.612900e-04
g__MGBC114844	6.659331e-05	4.105335e-04
g__Pelethomonas	6.618416e-05	2.448069e-04
g__Victivallis	6.489695e-05	4.051890e-04
g__RGIG9115	6.478642e-05	4.986757e-04
g__UBA1405	6.337712e-05	3.647934e-04
g__MGBC164599	6.309143e-05	2.415782e-04
g__UMGS1754	6.307099e-05	4.707822e-04
g__CAG-196	6.303657e-05	3.691902e-04
g__Fructobacillus	6.009139e-05	7.880912e-04
g__Anaeromassilibacillus	5.991756e-05	4.100453e-04
g__MGBC120314	5.725195e-05	5.476452e-04
g__JAAZGC01	5.557462e-05	5.355315e-04
g__CAG-314	5.351060e-05	4.224425e-04
g__Cellulosilyticum	5.332328e-05	3.808652e-04
g__Enterousia	5.188415e-05	4.191287e-04
g__UMGS687	5.126641e-05	4.219539e-04
g__Erysipelothrix	5.024616e-05	6.589722e-04
g__Holdemania	4.990583e-05	2.392481e-04
g__Limivicinus	4.957042e-05	6.142188e-04
g__RGIG4790	4.884680e-05	4.322050e-04
g__Enterococcus_D	4.788989e-05	4.103756e-04
g__UBA933	4.778105e-05	6.266426e-04
g__Copranaerobaculum	4.777314e-05	2.215807e-04
g__SIG603	4.629171e-05	3.498294e-04
g__CAKVBE01	4.606653e-05	6.041568e-04
g__Mobilisporobacter	4.560952e-05	4.555415e-04
g__QVMH01	4.504653e-05	2.212459e-04
g__Hydrogenoanaerobacterium	4.475602e-05	1.749987e-04
g__CALWRB01	4.428930e-05	1.565875e-04
g__HGM16780	4.234877e-05	3.457660e-04
g__JAFSEX01	4.208347e-05	5.006300e-04
g__CALWTV01	4.031353e-05	4.868653e-04
g__Ruminococcus	4.026239e-05	5.280363e-04
g__Providencia	3.947092e-05	4.865493e-04
g__Woodwardibium	3.918633e-05	1.936551e-04
g__Frigididesulfovibrio	3.840477e-05	5.036739e-04
g__Wohlfahrtiimonas	3.820192e-05	5.010134e-04
g__Eubacterium	3.408400e-05	1.552477e-04
g__Morganella	3.398929e-05	4.457653e-04
g__Enterococcus_J	3.334065e-05	4.372585e-04
g__Neoruminococcus	3.310136e-05	1.689688e-04
g__RUG13868	3.198945e-05	2.291845e-04
g__UBA1394	3.162426e-05	2.289144e-04
g__JAAZDN01	3.052698e-05	4.003575e-04
g__CAG-452	2.832554e-05	1.923112e-04
g__Paracoccus	2.776073e-05	3.101775e-04
g__JAILQS01	2.736465e-05	1.827364e-04
g__CAKNOI01	2.732478e-05	3.262900e-04
g__RGIG2219	2.626128e-05	1.876693e-04
g__CAJOJR01	2.582848e-05	2.076085e-04
g__Ventrousia	2.576615e-05	1.230955e-04
g__HGM13862	2.435275e-05	9.859687e-05
g__Methanoplasma	2.278412e-05	2.988110e-04
g__Heteroclostridium	2.072692e-05	1.253234e-04
g__RGIG5057	2.033912e-05	1.439685e-04
g__Heteroscilispira	2.015044e-05	1.254733e-04
g__RGIG3091	1.786547e-05	2.343035e-04
g__RGIG446	1.709062e-05	8.960743e-05
g__Lentilactobacillus	1.631166e-05	2.139254e-04
g__Microbacterium	1.467237e-05	1.924263e-04
g__Alloscillospira	1.272669e-05	1.020529e-04
g__CALXXL01	1.228690e-05	7.294195e-05
g__SIG208	6.550316e-06	5.024769e-05
g__CAKVLS01	6.485638e-06	5.776699e-05
g__JAGVVH01	5.663380e-06	7.427454e-05

genus_arrange <- genus_summary %>%
    group_by(genus) %>%
    summarise(mean=sum(relabun)) %>%
    filter(genus != "g__")%>%
    arrange(-mean) %>%
    select(genus) %>%
    mutate(genus= sub("^g__", "", genus)) %>%
    pull()

genus_summary %>%
    left_join(genome_metadata_all %>% select(genus,phylum) %>% unique(),by=join_by(genus==genus)) %>%
    left_join(sample_metadata_all,by=join_by(sample==sample)) %>%
    mutate(genus= sub("^g__", "", genus)) %>%
    filter(genus %in% genus_arrange[1:20]) %>%
    mutate(genus=factor(genus,levels=rev(genus_arrange[1:20]))) %>%
    filter(relabun > 0) %>%
    ggplot(aes(x=relabun, y=genus, group=genus, color=phylum)) +
        scale_color_manual(values=phylum_colors_all) +
        #geom_boxplot() +
        geom_jitter(alpha=0.5) + 
        facet_nested(. ~ species)+
        theme_minimal()

5.3 Compositional dissimilarities

beta_q0n <- genome_counts_filt_all %>%
  column_to_rownames(., "genome") %>%
  filter(rowSums(. != 0, na.rm = TRUE) > 0) %>%
  select_if(~!all(. == 0)) %>%
  hillpair(., q = 0)

beta_q1n <- genome_counts_filt_all %>%
  column_to_rownames(., "genome") %>%
  filter(rowSums(. != 0, na.rm = TRUE) > 0) %>%
  select_if(~!all(. == 0)) %>%
  hillpair(., q = 1)

beta_q1p <- genome_counts_filt_all %>%
  column_to_rownames(., "genome") %>%
  filter(rowSums(. != 0, na.rm = TRUE) > 0) %>%
  select_if(~!all(. == 0)) %>%
  hillpair(., q = 1, tree = genome_tree_all)

5.3.1 Richness dissimilarity plot

nmds_q0n <- beta_q0n$S %>%
  vegan::metaMDS(., trymax = 500, k = 2, trace=0) %>%
  vegan::scores() %>%
  as_tibble(., rownames = "sample") %>%
  dplyr::left_join(sample_metadata_all, by = "sample") %>%
  group_by(species,population) %>%
  mutate(x_cen = mean(NMDS1, na.rm = TRUE)) %>%
  mutate(y_cen = mean(NMDS2, na.rm = TRUE)) %>%
  ungroup()

nmds_q0n %>%
  ggplot(aes(x = NMDS1, y = NMDS2, color = species, fill = species, shape = population_type)) +
    geom_point(size = 2) +
    scale_color_manual(values=c("#f48153","#83d3d4","#2d8183","#910c07"))+
    #   stat_ellipse(aes(color = beta_q1n_nmds$Groups))+
    geom_segment(aes(x = x_cen, y = y_cen, xend = NMDS1, yend = NMDS2), alpha = 0.5) +
    theme_classic() +
    theme(
      axis.text.x = element_text(size = 12),
      axis.text.y = element_text(size = 12),
      axis.title = element_text(size = 20, face = "bold"),
      axis.text = element_text(face = "bold", size = 18),
      panel.background = element_blank(),
      axis.line = element_line(size = 0.5, linetype = "solid", colour = "black"),
      legend.text = element_text(size = 16),
      legend.title = element_text(size = 18),
      legend.position = "right", legend.box = "vertical"
    ) +
    labs(shape="Population type",color="Species",fill="Species")

5.3.2 Neutral diversity dissimilarity plot

nmds_q1n <- beta_q1n$S %>%
  vegan::metaMDS(., trymax = 500, k = 2, trace=0) %>%
  vegan::scores() %>%
  as_tibble(., rownames = "sample") %>%
  dplyr::left_join(sample_metadata_all, by = "sample") %>%
  group_by(species,population) %>%
  mutate(x_cen = mean(NMDS1, na.rm = TRUE)) %>%
  mutate(y_cen = mean(NMDS2, na.rm = TRUE)) %>%
  ungroup()

nmds_q1n %>%
  ggplot(aes(x = NMDS1, y = NMDS2, color = species, fill = species, shape = population_type)) +
    geom_point(size = 2) +
    scale_color_manual(values=c("#f48153","#83d3d4","#2d8183","#910c07"))+
    #   stat_ellipse(aes(color = beta_q1n_nmds$Groups))+
    geom_segment(aes(x = x_cen, y = y_cen, xend = NMDS1, yend = NMDS2), alpha = 0.5) +
    theme_classic() +
    theme(
      axis.text.x = element_text(size = 12),
      axis.text.y = element_text(size = 12),
      axis.title = element_text(size = 20, face = "bold"),
      axis.text = element_text(face = "bold", size = 18),
      panel.background = element_blank(),
      axis.line = element_line(size = 0.5, linetype = "solid", colour = "black"),
      legend.text = element_text(size = 16),
      legend.title = element_text(size = 18),
      legend.position = "right", legend.box = "vertical"
    ) +
    labs(shape="Population type",color="Species",fill="Species")

5.3.3 Phylogenetic diversity dissimilarity plot

nmds_q1p <- beta_q1p$S %>%
  vegan::metaMDS(., trymax = 500, k = 2, trace=0) %>%
  vegan::scores() %>%
  as_tibble(., rownames = "sample") %>%
  dplyr::left_join(sample_metadata_all, by = "sample") %>%
  group_by(species,population) %>%
  mutate(x_cen = mean(NMDS1, na.rm = TRUE)) %>%
  mutate(y_cen = mean(NMDS2, na.rm = TRUE)) %>%
  ungroup()

nmds_q1p %>%
  ggplot(aes(x = NMDS1, y = NMDS2, color = species, fill = species, shape = population_type)) +
    geom_point(size = 2) +
    scale_color_manual(values=c("#f48153","#83d3d4","#2d8183","#910c07"))+
    #   stat_ellipse(aes(color = beta_q1n_nmds$Groups))+
    geom_segment(aes(x = x_cen, y = y_cen, xend = NMDS1, yend = NMDS2), alpha = 0.5) +
    theme_classic() +
    theme(
      axis.text.x = element_text(size = 12),
      axis.text.y = element_text(size = 12),
      axis.title = element_text(size = 20, face = "bold"),
      axis.text = element_text(face = "bold", size = 18),
      panel.background = element_blank(),
      axis.line = element_line(size = 0.5, linetype = "solid", colour = "black"),
      legend.text = element_text(size = 16),
      legend.title = element_text(size = 18),
      legend.position = "right", legend.box = "vertical"
    ) +
    labs(shape="Population type",color="Species",fill="Species")